Nayan is a web-based platform designed to make learning more accessible for visually impaired users. It allows users to listen to their notes, adjust the audio speed, translate content between languages, interact with AI in real-time, generate quizzes, and even receive quick summaries—all through voice commands, without the need for visual interaction.
My inspiration for Nayan came from observing how technology and AI have transformed the way we learn and access information. However, I realized that visually impaired individuals face new challenges as more study materials move online. Nayan was created to address this gap and make learning more accessible for them.
- Listen to Notes: Users can listen to their notes and adjust audio speed for their comfort.
- Translation: Translate content between different languages.
- Real-time Q&A: Users can ask questions to AI in real-time and receive answers.
- Quiz Generation: Generate quizzes for active recall of the material.
- Quick Summaries: Get concise summaries for last-minute revision.
- Voice Commands: Activate features by simply pressing the space bar and speaking the desired command.
Nayan was built using:
- Python with Streamlit to create a user-friendly web-based application.
- ChatGPT API/Gemini API and DeepL API for generating responses, translations, and more.
- speech_recognition for voice command input.
- pytesseract for OCR to convert images into text.
The platform is designed to enhance the educational experience of visually impaired users by making it simple, accessible, and interactive.
Building Nayan came with its challenges:
- Implementing reliable tools for voice recognition and OCR.
- Ensuring the envisioned features were both functional and impactful.
- Creating an easy-to-use and accessible interface for visually impaired users.
I'm proud of how Nayan turned out. The integration of ChatGPT and DeepL APIs, and the successful implementation of voice commands, made the platform a powerful tool for accessible learning. Visually impaired users can now activate voice commands with just a press of the space bar, without needing outside help.
Working on Nayan gave me valuable insights into accessibility technology. It was my first time integrating the ChatGPT API and DeepL API, and I learned a lot about voice recognition. This project deepened my understanding of how to create tools that can truly make a difference.
- Advanced Navigation: Add the ability for users to navigate to specific sections of their notes.
- Voice-based Editing: Enable users to edit their notes using voice commands.
- Device Compatibility: Extend compatibility to iPhones, iPads, and Android devices.
Follow these instructions to get a copy of the project up and running on your local machine.
Ensure you have the following installed on your system:
- Python 3.x
- pip (Python package manager)
- Clone the Repository:
git clone https://github.com/Aryan4884/nayan_project.git
- Navigate to the Project Directory:
cd nayan_project - Install the Required Packages:
pip install -r requirements.txt
- Run the Python App:
python app.py
- Run the Streamlit App:
streamlit run app.py
- Access the App:
- Once the app is running, you can access it by navigating to
http://localhost:8501in your web browser.
- Once the app is running, you can access it by navigating to
- Press the Space Bar to start using the voice command feature.
- Follow the Voice Prompts to listen to your notes, translate content, interact with AI, and more.
If you wish to contribute to Nayan, feel free to open a pull request. For major changes, please open an issue first to discuss what you would like to change.
If you have any questions, feel free to contact me at:
- Email: [email protected]